Merge pull request 'Fixing issue #140' (#155) from I140_Convert_the_RSS_feeds_from_php_to_the_static_site into main

Reviewed-on: #155

site-generator

@@ -1,5 +1,7 @@
 #!/usr/bin/perl
 
+# {{{ POD documentation
+
 =head1 NAME
 
         site-generator - HPR Site Generator
@@ -36,7 +38,8 @@
 
 =head1 DESCRIPTION
 
-This is a site generator for the Hacker Public Radio website based upon the Perl Templates Toolkit.
+This is a site generator for the Hacker Public Radio website based upon the
+Perl Template Toolkit.
 
 =head1 INSTALLATION
 
@@ -74,6 +77,7 @@ This is a site generator for the Hacker Public Radio website based upon the Perl
                 * Tie::DBI
                 * DBD::SQLite or DBD:mysql
                 * Date::Calc
+                * Text::CSV_XS
 
 =head1 AUTHOR
 
@@ -99,15 +103,22 @@ This is a site generator for the Hacker Public Radio website based upon the Perl
 
 =cut
 
+# }}}
+
 use strict;
 use warnings;
 
 use Getopt::Long qw(:config auto_help);
 use Pod::Usage;
 use Config::Std;
+use Text::CSV_XS;
+use HTML::Entities qw(encode_entities_numeric);
 use Template;
 use Data::Dumper;
 
+binmode STDOUT, ":encoding(UTF-8)";
+binmode STDERR, ":encoding(UTF-8)";
+
 exit main();
 
 sub main {
@@ -149,6 +160,14 @@ sub main {
 
     my $tt = get_template_html($config{DBI}, $config{app_paths});
 
+    #
+    # Define a TT² vmethod called 'csv_parse', it takes a scalar value and
+    # returns an arrayref. Also define a filter called 'xml_entity' which
+    # numerically encodes non-ASCII characters.
+    #
+    $tt->context->define_vmethod( 'scalar', 'csv_parse', \&parse_csv );
+    $tt->context->define_filter( 'xml_entity', \&xml_entity );
+
     # If command line option all is set, parse configuration file
     # for all pages
     if ($all) {
@@ -184,7 +203,7 @@ sub main {
 
             if ($page_config->{'multipage'} && $page_config->{'multipage'} eq 'true') {
                 # Empty arrayref bug fixed, so count is reduced by 1
-#				if (scalar @{$parsed_arg{'ids'}} == 1) {
+                # was: if (scalar @{$parsed_arg{'ids'}} == 1) {
                 if (scalar @{$parsed_arg{'ids'}} == 0) {
                     @{$parsed_arg{'ids'}} = get_ids_from_db($tt, \$page_config);
                 }
@@ -212,9 +231,10 @@ sub get_template_html (\%@)  {
     # template start and end tags to also function as
     # HTML comments to make the template file valid HTML.
     #
-	return Template->new({
+    return Template->new(
-			INCLUDE_PATH => $_[1]{templates_path},
+        {   INCLUDE_PATH => $_[1]{templates_path},
             OUTPUT_PATH  => $_[1]{output_path},
+            ENCODING     => 'utf8',
             EVAL_PERL    => 1,
             START_TAG    => '<!--%',
             END_TAG      => '%-->',
@@ -226,17 +246,19 @@ sub get_template_html (\%@)  {
                 user     => $_[0]{user},
                 password => $_[0]{password},
             }
-		}) || die $Template::ERROR, "\n";
+        }
+    ) || die $Template::ERROR, "\n";
 
 }
 
 sub generate_page {
-	my ($tt, $config, $preview) = @_;
+    my ( $tt, $config, $preview ) = @_;
     my $html;
-	if (!$preview) {
+    if ( !$preview ) {
         $html = get_filename($$config);
     }
-	$tt->process($$config->{root_template}, $$config, $html)
+    $tt->process( $$config->{root_template},
+        $$config, $html, { binmode => ':utf8' } )
         || die $tt->error(), "\n";
 
 }
@@ -258,7 +280,6 @@ sub parse_page_arg {
     my ($page_arg) =  @_;
     # Split page name from page ids if available.
     my ($page, $ids) = split(/=/, $page_arg);
-	#my @ids = [];
     my @ids;
 
     if(!$ids) {
@@ -333,15 +354,68 @@ sub print_available_pages {
     # Load config file
     read_config "site.cfg" => my %config;
 
-	my @page_args = sort (keys %config);
+    my @page_args = sort ( keys %config );
 
     # Remove non page sections of the configuration file
     # from the generated list of pages.
-	@page_args= grep { $_ ne 'DBI' } @page_args;
+    @page_args = grep { $_ ne 'DBI' } @page_args;
-	@page_args= grep { $_ ne 'root_template' } @page_args;
+    @page_args = grep { $_ ne 'root_template' } @page_args;
 
     foreach my $page_arg (@page_args) {
         print "$page_arg\n";
     }
     exit;
 }
+
+#===  FUNCTION  ================================================================
+#         NAME: parse_csv
+#      PURPOSE: Parses a simple string containing CSV data
+#   PARAMETERS: $csv_in         CSV string
+#      RETURNS: An arrayref containing the parsed CSV elements
+#  DESCRIPTION: The Text::CSV_XS module instance is created with the option
+#               'allow_whitespace' to be forgiving of any spaces around the
+#               CSV elements and to strip them. Also, 'allow_loose_quotes' is
+#               forgiving of really messed up CSV.
+#       THROWS: No exceptions
+#     COMMENTS: None
+#     SEE ALSO: N/A
+#===============================================================================
+sub parse_csv {
+    my ($csv_in) = @_;
+
+    my $csv = Text::CSV_XS->new(
+        {   binary             => 1,
+            auto_diag          => 1,
+            allow_whitespace   => 1,
+            allow_loose_quotes => 1
+        }
+    );
+    my $status = $csv->parse($csv_in);
+    unless ( $status ) {
+        warn "Failed to parse '$csv_in'\n" ;
+        return;
+    }
+    my @fields = $csv->fields();
+
+    return \@fields;
+}
+
+#===  FUNCTION  ================================================================
+#         NAME: xml_entity
+#      PURPOSE: Static filter to encode Unicode for XML
+#   PARAMETERS: $text           String to be processed
+#      RETURNS: Processed text
+#  DESCRIPTION:
+#       THROWS: No exceptions
+#     COMMENTS: None
+#     SEE ALSO: N/A
+#===============================================================================
+sub xml_entity {
+    my ($text) = @_;
+
+    encode_entities_numeric( $text );
+
+    return $text;
+}
+
+# vim: syntax=perl:ts=8:sw=4:et:ai:tw=78:fo=tcrqn21:fdm=marker

templates/rss-query-hpr-mysql.tpl.xml

@@ -10,14 +10,17 @@
             hosts.local_image,
             hosts.hostid,
             hosts.host, hosts.email,
-	miniseries.name AS series, miniseries.id AS seriesid
+            miniseries.name AS series, miniseries.id AS seriesid,
+            assets.size AS length
         FROM eps
         INNER JOIN hosts ON eps.hostid = hosts.hostid
         INNER JOIN miniseries ON eps.series = miniseries.id
-	WHERE eps.date < DATE_ADD(NOW(), INTERVAL 1 DAY)
+        INNER JOIN assets ON eps.id = assets.episode_id
+        WHERE eps.date <= UTC_DATE()
+        AND assets.extension = ?
         ORDER BY eps.date DESC
         LIMIT 10
 ')
 %-->
-<!--% feed_result = query_hpr_feed.execute() %-->
+<!--% feed_result = query_hpr_feed.execute(media_file_extension) %-->
 

templates/rss-query-hpr-sqlite.tpl.xml

@@ -10,14 +10,17 @@
             hosts.local_image,
             hosts.hostid,
             hosts.host, hosts.email,
-	miniseries.name AS series, miniseries.id AS seriesid
+            miniseries.name AS series, miniseries.id AS seriesid,
+            assets.size AS length
         FROM eps
         INNER JOIN hosts ON eps.hostid = hosts.hostid
         INNER JOIN miniseries ON eps.series = miniseries.id
-	WHERE eps.date < date(\'now\', \'+1 days\')
+        INNER JOIN assets ON eps.id = assets.episode_id
+        WHERE eps.date <= date(\'now\')
+        AND assets.extension = ?
         ORDER BY eps.date DESC
         LIMIT 10
 ')
 %-->
-<!--% feed_result = query_hpr_feed.execute() %-->
+<!--% feed_result = query_hpr_feed.execute(media_file_extension) %-->
 

templates/rss-query-hpr_total-mysql.tpl.xml

@@ -10,13 +10,16 @@
             hosts.local_image,
             hosts.hostid,
             hosts.host, hosts.email,
-	miniseries.name AS series, miniseries.id AS seriesid
+            miniseries.name AS series, miniseries.id AS seriesid,
+            assets.size AS length
         FROM eps
         INNER JOIN hosts ON eps.hostid = hosts.hostid
         INNER JOIN miniseries ON eps.series = miniseries.id
-	WHERE eps.date < DATE_ADD(NOW(), INTERVAL 1 DAY)
+        INNER JOIN assets ON eps.id = assets.episode_id
+        WHERE eps.date < UTC_DATE()
+        AND assets.extension = ?
         ORDER BY eps.date DESC
 ')
 %-->
-<!--% feed_result = query_hpr_feed.execute() %-->
+<!--% feed_result = query_hpr_feed.execute(media_file_extension) %-->
 

templates/rss-query-hpr_total-sqlite.tpl.xml

@@ -10,13 +10,16 @@
             hosts.local_image,
             hosts.hostid,
             hosts.host, hosts.email,
-	miniseries.name AS series, miniseries.id AS seriesid
+            miniseries.name AS series, miniseries.id AS seriesid,
+            assets.size AS length
         FROM eps
         INNER JOIN hosts ON eps.hostid = hosts.hostid
         INNER JOIN miniseries ON eps.series = miniseries.id
-	WHERE eps.date < date(\'now\', \'+1 days\')
+        INNER JOIN assets ON eps.id = assets.episode_id
+        WHERE eps.date <= date(\'now\')
+        AND assets.extension = ?
         ORDER BY eps.date DESC
 ')
 %-->
-<!--% feed_result = query_hpr_feed.execute() %-->
+<!--% feed_result = query_hpr_feed.execute(media_file_extension) %-->
 

templates/rss.tpl.xml

@@ -39,7 +39,7 @@
   <image>
     <url>https://www.hackerpublicradio.org/images/hpr_feed_small.png</url>
     <title>Hacker Public Radio</title>
-    <link>https://www.hackerpublicradio.org/about.php</link>
+    <link>https://www.hackerpublicradio.org/about.html</link>
     <description>The Hacker Public Radio Old Microphone Logo</description>
     <height>164</height>
     <width>144</width>

templates/shared-episode-summary.tpl.html

@@ -12,7 +12,11 @@ from the series <em><a href="<!--% baseurl %-->series/<!--% zero_pad_left(series
 <!--% END %-->
 
 <!--% MACRO display_tags(tags) BLOCK %-->
-	<span><label>Tags:</label> <em><!--% tags %--></em>.</span>
+    <span><label>Tags:</label> <em>
+        <!--% FOREACH tag IN tags.csv_parse %-->
+        <a href="<!--% absolute_path(baseurl) %-->tags.html#<!--% tag.lower %-->"><!--% tag %--></a><!--% IF loop.count == loop.size %-->.<!--% ELSE %-->,<!--% END %-->
+        <!--% END %--></em>
+    </span>
 <!--% END %-->
 
 <!--% MACRO display_listen_in(eps_id, episode_type) BLOCK %-->

templates/shared-item.tpl.xml

@@ -1,5 +1,6 @@
 <!--% PROCESS 'shared-utils.tpl.html' %-->
 <!--% MACRO display_item(episode, file_extension, audio_mime_type) BLOCK %-->
+<!--% USE HTML.Strip %-->
 <!--% IF audio_mime_type == ""  %-->
 <!--% audio_mime_type = 'ogg' %-->
 <!--% END %-->
@@ -11,13 +12,13 @@
     <googleplay:author><!--% episode.email %--> (<!--% episode.host %-->)</googleplay:author>
     <itunes:author><!--% episode.email %--> (<!--% episode.host %-->)</itunes:author>
     <googleplay:image href="https://www.hackerpublicradio.org/images/hpr_feed_itunes.png"/>
-	<link>https://www.hackerpublicradio.org/eps/hpr/<!--% zero_pad_left(episode.id) %-->/index.html</link>
+    <link>https://www.hackerpublicradio.org/eps/hpr<!--% zero_pad_left(episode.id) %-->/index.html</link>
     <description><![CDATA[<!--% episode.notes %-->]]>
 </description>
-    <itunes:summary><![CDATA[<!--% episode.notes %-->]]>
+    <itunes:summary><![CDATA[<!--% episode.notes.substr(0, 4000) | html_strip | xml_entity %-->]]>
 </itunes:summary>
     <pubDate><!--% format_feed_date(episode.date) %--></pubDate>
-    <enclosure url="http://hackerpublicradio.org/eps/hpr<!--% zero_pad_left(episode.id) %-->.<!--% file_extension %-->" length="<!--% episode.duration * 1000 %-->" type="audio/<!--% audio_mime_type %-->"/>
+    <enclosure url="http://hackerpublicradio.org/eps/hpr<!--% zero_pad_left(episode.id) %-->.<!--% file_extension %-->" length="<!--% episode.length %-->" type="audio/<!--% audio_mime_type %-->"/>
     <guid>http://hackerpublicradio.org/eps/hpr<!--% zero_pad_left(episode.id) %-->.<!--% file_extension %--></guid>
   </item>
 <!--% END %-->

templates/shared-utils.tpl.html

@@ -93,7 +93,3 @@
     <!--% END %-->
     <a href="<!--% absolute_path(baseurl) %-->eps/<!--% folder %--><!--% zero_pad_left(links.latest) %-->/index.html" rel="last">Latest &gt;&gt;</a></small>
 <!--% END %-->
-
-<!--
-    vim: syntax=html:ts=8:sw=4:tw=78:et:ai:
--->